neonbjb/tortoise-tts
1
0
Fork 0
mirror of https://github.com/neonbjb/tortoise-tts.git synced 2026-02-17 21:24:21 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #511 from neonbjb/deepspeed_integration

Browse source 
revert deepspeed version due to crash in do_tts
This commit is contained in:
manmay nakhashi 2023-07-10 00:40:34 +05:30 committed by GitHub
parent 2cab3c6668 b8893a25f5
commit 8ad7364460
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
requirements.txt
View file

@ -18,4 +18,4 @@ appdirs
nbconvert==5.3.1
tornado==4.2
pydantic==1.9.0
deepspeed==9.0.0
deepspeed==0.8.3

4
tortoise/do_tts.py
View file

@ -13,6 +13,7 @@ if __name__ == '__main__':
parser.add_argument('--voice', type=str, help='Selects the voice to use for generation. See options in voices/ directory (and add your own!) '
'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='random')
parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='fast')
parser.add_argument('--use_deepspeed', type=str, help='Which voice preset to use.', default=False)
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/')
parser.add_argument('--model_dir', type=str, help='Where to find pretrained model checkpoints. Tortoise automatically downloads these to .models, so this'
'should only be specified if you have custom checkpoints.', default=MODELS_DIR)
@ -23,8 +24,7 @@ if __name__ == '__main__':
'Increasing this can in some cases reduce the likelihood of multiple speakers. Defaults to 0 (disabled)', default=.0)
args = parser.parse_args()
os.makedirs(args.output_path, exist_ok=True)
tts = TextToSpeech(models_dir=args.model_dir)
tts = TextToSpeech(models_dir=args.model_dir, use_deepspeed=args.use_deepspeed)
selected_voices = args.voice.split(',')
for k, selected_voice in enumerate(selected_voices):